Compare commits

base: huggingface:main

Branches Tags

huggingface:main

huggingface:add_vlm_chunking

huggingface:add_chunked_atn

huggingface:flashinfer-0.2.5

huggingface:gaudi/add-ci

huggingface:kvrouter-endpoints

huggingface:add_chunked_attn

huggingface:chunked_attn_l4

huggingface:git_v3.2.3

huggingface:git_v3.2.2

huggingface:add_L4

huggingface:aiter_kernels

huggingface:message-more-info

huggingface:improve-tool-call-and-response-ids

huggingface:pr-2982-ci-branch

huggingface:enable-transformers-vlm

huggingface:git_3.2.1

huggingface:debugging-timeouts

huggingface:use_updated_kernels

huggingface:git_3.2.0

huggingface:origin/slind_window_fix

huggingface:no_root_user2

huggingface:no_root_user

huggingface:git_3.1.1

huggingface:tmp_invariants

huggingface:proxy_sse_engine_state

huggingface:pr-2954-ci-branch

huggingface:neuron_backend_ci_test

huggingface:zstd

huggingface:pr-3018-ci-branch

huggingface:pr-3002-ci-branch

huggingface:adjust-mllama-test-output

huggingface:pr-3004-ci-branch

huggingface:triton_fix

huggingface:git_v3.1.0

huggingface:kvrouter

huggingface:vllm/setup

huggingface:gha_sccache_use_secrets

huggingface:add_deepseekv3

huggingface:more_logs

huggingface:fix-tp

huggingface:git_v3.0.2

huggingface:new_minor_version

huggingface:enable-qwen2vl-video

huggingface:response-header-metrics

huggingface:nix/pytorch-2.5.1

huggingface:baichuan2-13b

huggingface:update-jsonschema

huggingface:ci-update_xpu_image

huggingface:pr-2840-ci-branch

huggingface:fix_fp8_llama3.2

huggingface:feat-backend-llamacpp

huggingface:s3-cache

huggingface:git_v3.0.1

huggingface:trtllm/executor_stats

huggingface:git_v3.0.0

huggingface:pr-2784-ci-branch

huggingface:git_v2.4.1

huggingface:ipex-moe

huggingface:pr-2711-ci-branch

huggingface:trtllm-stop-words

huggingface:upgrade-outlines

huggingface:git_v2.4.0

huggingface:auto_length

huggingface:close_dl_thread

huggingface:adjust-where-request-max-tokens-is-defaulted

huggingface:feature/machete

huggingface:add-test-for-warmup-and-kvcache

huggingface:add-rotary-embed-tests

huggingface:bugfix/moe-kernels-imports

huggingface:add-google-cloud-provider

huggingface:add_tunable_prefill

huggingface:enable-non-grammar-constrained-tools

huggingface:git_v2.3.1

huggingface:nix/docker2

huggingface:ci_amd

huggingface:ci_amd4

huggingface:fp8_rocm

huggingface:cuda_ipc_allreduce

huggingface:mllama

huggingface:rocm_6.2_fixes

huggingface:tuna

huggingface:git_v2.3.0

huggingface:nix_integration_tests

huggingface:feature/moe-kernels

huggingface:prefix_chunk

huggingface:pr-2444-ci-branch

huggingface:pr-2517-ci-branch

huggingface:nix_test2

huggingface:feature/vlm-prefix-caching

huggingface:feat/add-load-test

huggingface:upgrade_mlp_speculator

huggingface:avoid-cuda-graph-during-warmup-if-oom

huggingface:fix/op-trace-id

huggingface:prefix_default

huggingface:fix_exl2

huggingface:exl2

huggingface:fix-repack-for-marlin

huggingface:fix-release-tests

huggingface:explore-t4-gemma-issues

huggingface:feature/radix-prefix-cache

huggingface:nix/cargo-clippy

huggingface:pr-2366-ci-branch

huggingface:feature/radix-prefix-cache-bench

huggingface:inlcude-latest-release-on-commit-builds-tags

huggingface:feature/no_repeat_ngram_size_ci

huggingface:fix/parse-mamba-config

huggingface:backends/trtllm-executor

huggingface:pr-2290-ci-runner

huggingface:feature/no_repeat_ngram_size

huggingface:add_api_key

huggingface:use_g6

huggingface:feat/max_queue_size

huggingface:git_v2.2.0

huggingface:debug/gemma2

huggingface:fix_mistral2

huggingface:refactor-lora-linear

huggingface:development-guide

huggingface:feature/prefix

huggingface:ci_amd3

huggingface:experiment/moe

huggingface:fix/allow-top-p-0

huggingface:ci-new-cluster

huggingface:git_v2.1.1

huggingface:add-small-ttft-script

huggingface:test-batch-speedup-amount

huggingface:fp8_kvcache

huggingface:add-chat-response-format

huggingface:fix-mixtral-adapter-loading

huggingface:backends/trtllm

huggingface:git_v2.1.0

huggingface:automodel-supports-flash-paged-attention

huggingface:feat/backend_abstraction

huggingface:ci2

huggingface:temp_work

huggingface:bugfix/phi-exl2

huggingface:multi-lora

huggingface:debug-torch-23

huggingface:feat/backend_feature

huggingface:pr-2076-ci-run

huggingface:maintenance/docker-network

huggingface:ci-patch

huggingface:feat/page_re_alloc

huggingface:feature/phi-3-small

huggingface:debug-gpt2

huggingface:amd-ci-fx

huggingface:ci_amd2

huggingface:support-phi3-small

huggingface:set-num-blocks

huggingface:rocm-ci-build

huggingface:ci-xpu2

huggingface:maintenance/merge-vlm-input-prep

huggingface:fix_phi3

huggingface:precompile-kernels-workflow

huggingface:support-pre-compile-kernels

huggingface:pip-installable

huggingface:flashinfer

huggingface:update_internal_version

huggingface:git_2.0.4

huggingface:pr-1869-ci-run

huggingface:fix-cudagraph-bug

huggingface:fix-version-install

huggingface:improve-dynamic-message-content

huggingface:ci-run-openai-function-calling-compatible-support

huggingface:mi300-temp

huggingface:dummy

huggingface:ci-xpu

huggingface:bugfix/add_tools_prompt

huggingface:martinigoyanes-fix-frequency-penalty

huggingface:add-quickstart-script

huggingface:skip-mistral-test

huggingface:fix_default_arg

huggingface:fix-grammar-cleanup-bug

huggingface:llama-fused-compiled-mlp

huggingface:explore-static-triton-kernels

huggingface:improve_defaults

huggingface:tmp_medusa

huggingface:improve_launcher_defaults

huggingface:op-compilation-benchmarking

huggingface:fix-grammar-fsm-batching

huggingface:tmp_torch_compile

huggingface:test_rocm

huggingface:router-grammar-compile

huggingface:bump-client-0.6.2

huggingface:avoid-zero-seed

huggingface:adding_docs

huggingface:feat/flash_decoding

huggingface:fix-gemma-tokenization

huggingface:ci-amihalik-update-chat-completion-messages

huggingface:add_batch_dimension

huggingface:update_peft

huggingface:add_readme_dashboard

huggingface:revert

huggingface:debug-request-id

huggingface:update_readme

huggingface:mamba2

huggingface:fix_neox_rotary_emb

huggingface:bump-poetry-and-requirements

huggingface:update_docs2

huggingface:support-phi-model

huggingface:fix/avoid_record_streams

huggingface:medusa

huggingface:feat/cuda_12

huggingface:feat/attention_sinks

huggingface:dev

huggingface:speculative

huggingface:self-generating-docs

huggingface:improve-docs

huggingface:fix_leak

huggingface:streaming_conceptual

huggingface:test_docs

huggingface:osanseviero-patch-1

huggingface:model_compat_log

huggingface:compat_logger

huggingface:simpler_exllama

huggingface:bnb4

huggingface:enable_non_divisible_embeddings

huggingface:feat/better_tokens

huggingface:add_integration_test

huggingface:add_gptq_docs

huggingface:quantization

huggingface:remove_post_load_weights

huggingface:feat/improve_max_tokens

huggingface:feat/parse_logs

huggingface:deploy/aml

huggingface:megatron

huggingface:feat/support_deepspeed

huggingface:v3.2.3

huggingface:v3.2.2

huggingface:v3.2.1

huggingface:v3.2.0

huggingface:v3.1.1

huggingface:v3.1.0

huggingface:v3.0.2

huggingface:v3.0.1

huggingface:v3.0.0

huggingface:v2.4.1

huggingface:v2.4.0

huggingface:v2.3.1

huggingface:v2.3.0

huggingface:v2.2.0

huggingface:v2.1.1

huggingface:v2.1.0

huggingface:v2.0.4

huggingface:v2.0.3

huggingface:v2.0.2

huggingface:v2.0.1

huggingface:v2.0.0

huggingface:v1.4.5

huggingface:v1.4.4

huggingface:v1.4.3

huggingface:v1.4.2

huggingface:v1.4.1

huggingface:v1.4.0

huggingface:v1.3.4

huggingface:v1.3.3

huggingface:v1.3.2

huggingface:v1.3.1

huggingface:v1.3.0

huggingface:v1.2.0

huggingface:v1.1.1

huggingface:v1.1.0

huggingface:v1.0.3

huggingface:v1.0.2

huggingface:v1.0.1

huggingface:v1.0.0

huggingface:v0.9.4

huggingface:v0.9.3

huggingface:v0.9.2

huggingface:v0.9.1

huggingface:v0.9.0

huggingface:v0.8.2

huggingface:v0.8.1

huggingface:v0.8.0

huggingface:v0.7.0

huggingface:v0.6.0

huggingface:v0.5.0

huggingface:v0.4.3

huggingface:v0.4.2

huggingface:v0.4.1

huggingface:v0.4.0

huggingface:v0.3.2

huggingface:v0.3.1

huggingface:v0.3.0

huggingface:v0.2.1

huggingface:v0.2.0

...

compare: huggingface:v2.0.2

Branches Tags

huggingface:add_vlm_chunking

huggingface:main

huggingface:add_chunked_atn

huggingface:flashinfer-0.2.5

huggingface:gaudi/add-ci

huggingface:kvrouter-endpoints

huggingface:add_chunked_attn

huggingface:chunked_attn_l4

huggingface:git_v3.2.3

huggingface:git_v3.2.2

huggingface:add_L4

huggingface:aiter_kernels

huggingface:message-more-info

huggingface:improve-tool-call-and-response-ids

huggingface:pr-2982-ci-branch

huggingface:enable-transformers-vlm

huggingface:git_3.2.1

huggingface:debugging-timeouts

huggingface:use_updated_kernels

huggingface:git_3.2.0

huggingface:origin/slind_window_fix

huggingface:no_root_user2

huggingface:no_root_user

huggingface:git_3.1.1

huggingface:tmp_invariants

huggingface:proxy_sse_engine_state

huggingface:pr-2954-ci-branch

huggingface:neuron_backend_ci_test

huggingface:zstd

huggingface:pr-3018-ci-branch

huggingface:pr-3002-ci-branch

huggingface:adjust-mllama-test-output

huggingface:pr-3004-ci-branch

huggingface:triton_fix

huggingface:git_v3.1.0

huggingface:kvrouter

huggingface:vllm/setup

huggingface:gha_sccache_use_secrets

huggingface:add_deepseekv3

huggingface:more_logs

huggingface:fix-tp

huggingface:git_v3.0.2

huggingface:new_minor_version

huggingface:enable-qwen2vl-video

huggingface:response-header-metrics

huggingface:nix/pytorch-2.5.1

huggingface:baichuan2-13b

huggingface:update-jsonschema

huggingface:ci-update_xpu_image

huggingface:pr-2840-ci-branch

huggingface:fix_fp8_llama3.2

huggingface:feat-backend-llamacpp

huggingface:s3-cache

huggingface:git_v3.0.1

huggingface:trtllm/executor_stats

huggingface:git_v3.0.0

huggingface:pr-2784-ci-branch

huggingface:git_v2.4.1

huggingface:ipex-moe

huggingface:pr-2711-ci-branch

huggingface:trtllm-stop-words

huggingface:upgrade-outlines

huggingface:git_v2.4.0

huggingface:auto_length

huggingface:close_dl_thread

huggingface:adjust-where-request-max-tokens-is-defaulted

huggingface:feature/machete

huggingface:add-test-for-warmup-and-kvcache

huggingface:add-rotary-embed-tests

huggingface:bugfix/moe-kernels-imports

huggingface:add-google-cloud-provider

huggingface:add_tunable_prefill

huggingface:enable-non-grammar-constrained-tools

huggingface:git_v2.3.1

huggingface:nix/docker2

huggingface:ci_amd

huggingface:ci_amd4

huggingface:fp8_rocm

huggingface:cuda_ipc_allreduce

huggingface:mllama

huggingface:rocm_6.2_fixes

huggingface:tuna

huggingface:git_v2.3.0

huggingface:nix_integration_tests

huggingface:feature/moe-kernels

huggingface:prefix_chunk

huggingface:pr-2444-ci-branch

huggingface:pr-2517-ci-branch

huggingface:nix_test2

huggingface:feature/vlm-prefix-caching

huggingface:feat/add-load-test

huggingface:upgrade_mlp_speculator

huggingface:avoid-cuda-graph-during-warmup-if-oom

huggingface:fix/op-trace-id

huggingface:prefix_default

huggingface:fix_exl2

huggingface:exl2

huggingface:fix-repack-for-marlin

huggingface:fix-release-tests

huggingface:explore-t4-gemma-issues

huggingface:feature/radix-prefix-cache

huggingface:nix/cargo-clippy

huggingface:pr-2366-ci-branch

huggingface:feature/radix-prefix-cache-bench

huggingface:inlcude-latest-release-on-commit-builds-tags

huggingface:feature/no_repeat_ngram_size_ci

huggingface:fix/parse-mamba-config

huggingface:backends/trtllm-executor

huggingface:pr-2290-ci-runner

huggingface:feature/no_repeat_ngram_size

huggingface:add_api_key

huggingface:use_g6

huggingface:feat/max_queue_size

huggingface:git_v2.2.0

huggingface:debug/gemma2

huggingface:fix_mistral2

huggingface:refactor-lora-linear

huggingface:development-guide

huggingface:feature/prefix

huggingface:ci_amd3

huggingface:experiment/moe

huggingface:fix/allow-top-p-0

huggingface:ci-new-cluster

huggingface:git_v2.1.1

huggingface:add-small-ttft-script

huggingface:test-batch-speedup-amount

huggingface:fp8_kvcache

huggingface:add-chat-response-format

huggingface:fix-mixtral-adapter-loading

huggingface:backends/trtllm

huggingface:git_v2.1.0

huggingface:automodel-supports-flash-paged-attention

huggingface:feat/backend_abstraction

huggingface:ci2

huggingface:temp_work

huggingface:bugfix/phi-exl2

huggingface:multi-lora

huggingface:debug-torch-23

huggingface:feat/backend_feature

huggingface:pr-2076-ci-run

huggingface:maintenance/docker-network

huggingface:ci-patch

huggingface:feat/page_re_alloc

huggingface:feature/phi-3-small

huggingface:debug-gpt2

huggingface:amd-ci-fx

huggingface:ci_amd2

huggingface:support-phi3-small

huggingface:set-num-blocks

huggingface:rocm-ci-build

huggingface:ci-xpu2

huggingface:maintenance/merge-vlm-input-prep

huggingface:fix_phi3

huggingface:precompile-kernels-workflow

huggingface:support-pre-compile-kernels

huggingface:pip-installable

huggingface:flashinfer

huggingface:update_internal_version

huggingface:git_2.0.4

huggingface:pr-1869-ci-run

huggingface:fix-cudagraph-bug

huggingface:fix-version-install

huggingface:improve-dynamic-message-content

huggingface:ci-run-openai-function-calling-compatible-support

huggingface:mi300-temp

huggingface:dummy

huggingface:ci-xpu

huggingface:bugfix/add_tools_prompt

huggingface:martinigoyanes-fix-frequency-penalty

huggingface:add-quickstart-script

huggingface:skip-mistral-test

huggingface:fix_default_arg

huggingface:fix-grammar-cleanup-bug

huggingface:llama-fused-compiled-mlp

huggingface:explore-static-triton-kernels

huggingface:improve_defaults

huggingface:tmp_medusa

huggingface:improve_launcher_defaults

huggingface:op-compilation-benchmarking

huggingface:fix-grammar-fsm-batching

huggingface:tmp_torch_compile

huggingface:test_rocm

huggingface:router-grammar-compile

huggingface:bump-client-0.6.2

huggingface:avoid-zero-seed

huggingface:adding_docs

huggingface:feat/flash_decoding

huggingface:fix-gemma-tokenization

huggingface:ci-amihalik-update-chat-completion-messages

huggingface:add_batch_dimension

huggingface:update_peft

huggingface:add_readme_dashboard

huggingface:revert

huggingface:debug-request-id

huggingface:update_readme

huggingface:mamba2

huggingface:fix_neox_rotary_emb

huggingface:bump-poetry-and-requirements

huggingface:update_docs2

huggingface:support-phi-model

huggingface:fix/avoid_record_streams

huggingface:medusa

huggingface:feat/cuda_12

huggingface:feat/attention_sinks

huggingface:dev

huggingface:speculative

huggingface:self-generating-docs

huggingface:improve-docs

huggingface:fix_leak

huggingface:streaming_conceptual

huggingface:test_docs

huggingface:osanseviero-patch-1

huggingface:model_compat_log

huggingface:compat_logger

huggingface:simpler_exllama

huggingface:bnb4

huggingface:enable_non_divisible_embeddings

huggingface:feat/better_tokens

huggingface:add_integration_test

huggingface:add_gptq_docs

huggingface:quantization

huggingface:remove_post_load_weights

huggingface:feat/improve_max_tokens

huggingface:feat/parse_logs

huggingface:deploy/aml

huggingface:megatron

huggingface:feat/support_deepspeed

huggingface:v3.2.3

huggingface:v3.2.2

huggingface:v3.2.1

huggingface:v3.2.0

huggingface:v3.1.1

huggingface:v3.1.0

huggingface:v3.0.2

huggingface:v3.0.1

huggingface:v3.0.0

huggingface:v2.4.1

huggingface:v2.4.0

huggingface:v2.3.1

huggingface:v2.3.0

huggingface:v2.2.0

huggingface:v2.1.1

huggingface:v2.1.0

huggingface:v2.0.4

huggingface:v2.0.3

huggingface:v2.0.2

huggingface:v2.0.1

huggingface:v2.0.0

huggingface:v1.4.5

huggingface:v1.4.4

huggingface:v1.4.3

huggingface:v1.4.2

huggingface:v1.4.1

huggingface:v1.4.0

huggingface:v1.3.4

huggingface:v1.3.3

huggingface:v1.3.2

huggingface:v1.3.1

huggingface:v1.3.0

huggingface:v1.2.0

huggingface:v1.1.1

huggingface:v1.1.0

huggingface:v1.0.3

huggingface:v1.0.2

huggingface:v1.0.1

huggingface:v1.0.0

huggingface:v0.9.4

huggingface:v0.9.3

huggingface:v0.9.2

huggingface:v0.9.1

huggingface:v0.9.0

huggingface:v0.8.2

huggingface:v0.8.1

huggingface:v0.8.0

huggingface:v0.7.0

huggingface:v0.6.0

huggingface:v0.5.0

huggingface:v0.4.3

huggingface:v0.4.2

huggingface:v0.4.1

huggingface:v0.4.0

huggingface:v0.3.2

huggingface:v0.3.1

huggingface:v0.3.0

huggingface:v0.2.1

huggingface:v0.2.0

The selected branch/tag are equal.